---
language:
- vi
- ede

tags:
- splade
- unigram
- sentencepiece
- information-retrieval
- cross-lingual-retrieval
- EViRAL
---

# SPLADE + Unigram Tokenizer — EViRAL

Cross-lingual retrieval model for:

Ede query → Vietnamese passage retrieval

## Files

| File | Description |
|---|---|
| mlm.pt | MLM pre-trained SPLADE encoder |
| align.pt | Cross-lingual aligned encoder |
| finetune.pt | Fine-tuned retrieval encoder |
| spm_tokenizer/spm.model | SentencePiece unigram model |
| spm_tokenizer/spm.vocab | SentencePiece vocabulary |

## Tokenizer

Tokenizer type: SentencePiece Unigram